Although graph neural networks (GNNs) have achieved impressive achievements in graph classification, they often need abundant task-specific labels, which could be extensively costly to acquire. A credible solution is to explore additional labeled graphs to enhance unsupervised learning on the target domain. However, how to apply GNNs to domain adaptation remains unsolved owing to the insufficient exploration of graph topology and the significant domain discrepancy. In this paper, we propose \underline{Co}upled \underline{Co}ntrastive Graph Representation Learning (\method{}), which extracts the topological information from coupled learning branches and reduces the domain discrepancy with coupled contrastive learning. \method{} contains a graph convolutional network branch and a hierarchical graph kernel network branch, which explore graph topology in implicit and explicit manners. Besides, we incorporate coupled branches into a holistic multi-view contrastive learning framework, which not only incorporates graph representations learned from complementary views for enhanced understanding, but also encourages the similarity between cross-domain example pairs with the same semantics for domain alignment. Extensive experiments on various popular datasets show that \method{} outperforms these competing baselines by 5.7\% to 21.0\% generally.

翻译：摘要：尽管图神经网络（GNN）在图分类任务中取得了显著成就，但其通常需要大量任务特定标签，获取这些标签的代价极为高昂。一种可靠的解决方案是探索额外带标签图以增强目标域上的无监督学习。然而，由于图拓扑结构探索不足及显著的域差异，如何将GNN应用于域自适应仍是一个未解难题。本文提出耦合对比图表示学习（CoCo）方法，该方法从耦合学习分支中提取拓扑信息，并通过耦合对比学习减少域差异。CoCo包含一个图卷积网络分支和一个分层图核网络分支，分别以隐式和显式方式探索图拓扑结构。此外，我们将耦合分支融入一个整体多视角对比学习框架，该框架不仅融合从互补视角学习到的图表示以增强理解，还鼓励具有相同语义的跨域样本对之间实现相似性对齐。在多种主流数据集上的大量实验表明，CoCo通常以5.7%至21.0%的优势超越对比基线方法。